INDEX

Explanations

elements related to formatting or structure in documents

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ãĤº

-0.16

andas

-0.15

 Brow

-0.15

entiful

-0.14

lou

-0.14

oufl

-0.14

 Icon

-0.14

untlet

-0.13

Esc

-0.13

.router

-0.13

POSITIVE LOGITS

Ĥæķ°

0.16

-END

0.15

uy

0.15

Ã¤d

0.14

odor

0.14

uka

0.14

ophobic

0.13

/grpc

0.13

.edu

0.13

dsn

0.13

Activations Density 0.003%

elements related to formatting or structure in documents

No Comments

No Known Activations